CN113792782A - Track monitoring method and device for operating vehicle, storage medium and computer equipment - Google Patents
Track monitoring method and device for operating vehicle, storage medium and computer equipment Download PDFInfo
- Publication number
- CN113792782A CN113792782A CN202111069904.6A CN202111069904A CN113792782A CN 113792782 A CN113792782 A CN 113792782A CN 202111069904 A CN202111069904 A CN 202111069904A CN 113792782 A CN113792782 A CN 113792782A
- Authority
- CN
- China
- Prior art keywords
- track
- vehicle
- monitored
- data
- service type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 36
- 230000002159 abnormal effect Effects 0.000 claims abstract description 28
- 238000007637 random forest analysis Methods 0.000 claims abstract description 26
- 238000003066 decision tree Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000012806 monitoring device Methods 0.000 claims description 6
- 230000001174 ascending effect Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The invention discloses a track monitoring method and device for an operating vehicle, a storage medium and computer equipment. The method comprises the following steps: acquiring track data and a service type of a vehicle to be monitored; determining a track prediction model corresponding to the vehicle to be monitored according to the service type of the vehicle to be monitored, wherein the track prediction model is obtained based on isolated forest algorithm and random forest algorithm training; and inputting the track data of the vehicle to be monitored into the track prediction model to obtain the track abnormal probability value of the vehicle to be monitored. The method is based on the isolated forest algorithm and the random forest algorithm to train and obtain the track prediction model, and the track abnormity probability value of the vehicle to be monitored is predicted through the track prediction model, so that the probability of track abnormity of the operating vehicle can be timely and accurately monitored, and the timeliness and the accuracy of the running track monitoring of the operating vehicle are effectively improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence and big data processing, in particular to a track monitoring method and device for an operating vehicle, a storage medium and computer equipment.
Background
With the rapid development of the automobile industry in China and the continuous improvement of the living standard of the nation, the automobile gradually becomes a very important transportation tool in the life of residents. In this context, car rental services are also becoming increasingly popular with the market as they cater to the demand of temporary car use by some users.
Generally, the operating vehicles (rented vehicles) can be divided into a plurality of types according to the service types, such as a long rental type, a short rental type, a network contract rented type, a network contract self-sustaining type, and the like. In order to avoid various problems such as loss, modification and damage of various types of operating vehicles during operation, a renter usually installs a GPS device on the operating vehicle and then monitors the running track and the vehicle position of the operating vehicle in real time through the GPS device.
In the prior art, a vehicle renter usually determines whether an operating vehicle has an operating risk by monitoring indexes such as whether a track of the operating vehicle frequently enters a dangerous road section, whether the operating vehicle frequently stops near a used vehicle market or a car repair shop, and whether the operating vehicle travels too far. However, the simple track monitoring method cannot help the vehicle renter to know the actual operation risk of the operating vehicle timely and accurately, and because the operating vehicles are of a plurality of types and the running tracks of the various types are different, the monitoring difficulty of the operating vehicle is increased, the overall accuracy of monitoring the track of the operating vehicle is reduced, and finally the property of the vehicle renter is lost.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, a storage medium, and a computer device for monitoring a trajectory of an operating vehicle, and mainly aims to solve the technical problem that the travel trajectory monitoring of the operating vehicle is inefficient and inaccurate.
According to a first aspect of the present invention, there is provided a trajectory monitoring method of operating a vehicle, the method comprising:
acquiring track data and a service type of a vehicle to be monitored;
determining a track prediction model corresponding to the vehicle to be monitored according to the service type of the vehicle to be monitored, wherein the track prediction model is obtained based on isolated forest algorithm and random forest algorithm training;
and inputting the track data of the vehicle to be monitored into a track prediction model to obtain the track abnormal probability value of the vehicle to be monitored.
According to a second aspect of the present invention, there is provided a trajectory monitoring device for operating a vehicle, the device comprising:
the data acquisition module is used for acquiring the track data and the service type of the vehicle to be monitored;
the model determining module is used for determining a track prediction model corresponding to the vehicle to be monitored according to the service type of the vehicle to be monitored, wherein the track prediction model is obtained based on isolated forest algorithm and random forest algorithm training;
and the data processing module is used for inputting the track data of the vehicle to be monitored into the track prediction model to obtain the track abnormal probability value of the vehicle to be monitored.
According to a third aspect of the present invention, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described method of trajectory monitoring of an operating vehicle.
According to a fourth aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-described method of trajectory monitoring of a vehicle in operation when executing the program.
According to the track monitoring method, the track monitoring device, the storage medium and the computer equipment of the operating vehicle, track data and the service type of the vehicle to be monitored are firstly obtained, then a track prediction model corresponding to the vehicle to be monitored is determined according to the service type, and finally the track abnormal probability value of the vehicle to be monitored is obtained through the track prediction model. In the method, the track prediction model is obtained by training based on an isolated forest algorithm and a random forest algorithm, wherein the isolated forest algorithm can separate a normal track and an abnormal track in a sample, so that sufficient pre-judged sample data is provided for the random forest algorithm, and the random forest algorithm can accurately predict the abnormal probability of the track data according to the pre-judged sample data, so that the probability of track abnormality of the operating vehicle is timely and accurately monitored, and the timeliness and the accuracy of the monitoring of the running track of the operating vehicle are effectively improved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a track monitoring method for operating a vehicle according to an embodiment of the present invention,
FIG. 2 is a flow chart of a method for training a trajectory prediction model according to an embodiment of the present invention,
fig. 3 is a schematic structural diagram illustrating a track monitoring device for a vehicle in operation according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In one embodiment, as shown in fig. 1, a trajectory monitoring method for operating a vehicle is provided, which is described by taking the method as an example of being applied to a computer device such as a server, and includes the following steps:
101. and acquiring the track data and the service type of the vehicle to be monitored.
The vehicle to be monitored refers to an operating vehicle which needs track monitoring, and the operating vehicle refers to a vehicle which is provided for a vehicle lessee or an individual driver by a vehicle operator or a vehicle lessor in a renting, self-operation and other modes. Generally, the operating vehicles can be divided into a plurality of different service types according to different renting, renting and self-operation modes, such as long renting, short renting, network contract renting and network contract self-operation, and the like. In this embodiment, the computer device may acquire the trajectory data of the vehicle to be monitored in real time through a GPS device installed on the vehicle to be monitored, and may acquire the current service type of the vehicle to be monitored in the database according to the vehicle identifier (such as the license plate number) of the vehicle to be monitored. It is understood that the number of vehicles to be monitored may be one or more, and the type of traffic of the vehicles to be monitored may vary according to the actual operation mode. For ease of explanation of the specific meaning of the service types for operating a vehicle, several definitions of service types are provided below for reference.
In the embodiment, the long rental refers to that the vehicle rental contract is more than 6 months, the lessee is mainly an enterprise unit, and the lessee is used as a public vehicle of the enterprise unit during the execution period of the contract, and a driver is arranged by the lessee independently. Short rental refers to a vehicle rental contract that does not exceed 60 days, where the lessee is dominated by individual customers and is used by the lessee's customers during contract execution. The network appointment renting refers to a taxi belonging to the vehicle, and the individual driver rents the vehicle on the network appointment platform to carry out network appointment service to obtain payment and pay rent. The network appointment self-operation means that vehicles belong to a network appointment platform, the platform automatically recruits drivers and trains, the drivers open network appointment services, and the platform pays the driver rewards. It should be noted that, besides the above-mentioned several service types, the operating vehicle may have other service types, and this embodiment is not listed here.
102. And determining a track prediction model corresponding to the vehicle to be monitored according to the service type of the vehicle to be monitored, wherein the track prediction model is obtained based on isolated forest algorithm and random forest algorithm training.
The track prediction model is a model for predicting the track of the operating vehicle, the input of the model is track data of the operating vehicle, the output of the model is track abnormal probability value of the operating vehicle, and the track abnormal probability value can be used for acquiring the probability of the track abnormity of the vehicle to be monitored, namely the higher the track abnormal probability value is, the higher the operating risk of the vehicle to be monitored is, and otherwise, the lower the operating risk of the vehicle to be monitored is.
Specifically, the track prediction models can be different according to different types of operating vehicles, namely, each service type corresponds to a corresponding track prediction model, and by the method, the accuracy of track monitoring of operating vehicles with different service types can be improved. In this embodiment, before the model training, sample data may be classified first, and then a corresponding trajectory prediction model is trained according to the classified data samples corresponding to each service type, so as to obtain a trajectory prediction model corresponding to each service type. In addition, the track prediction model corresponding to each service type can be obtained by training an isolated forest algorithm and a random forest algorithm. The isolated forest algorithm is an unsupervised anomaly detection method suitable for continuous data, namely, anomaly data in a sample can be separated out without a marked sample; the random forest algorithm is an algorithm for integrating a plurality of decision trees into a classification model in an ensemble learning mode. Specifically, isolated abnormal sample data in a large amount of data can be accurately found out through a random sample segmentation strategy of an isolated forest algorithm, namely abnormal track data in a large amount of historical track data are found out, then a large amount of historical track samples are subjected to secondary classification through a trained isolated forest model, namely the historical track data are divided into normal tracks and abnormal tracks, finally, the classified historical track data are used as samples of a random forest, a plurality of decision trees in the random forest are trained, and finally, a track prediction model capable of predicting track abnormal probability values is obtained.
103. And inputting the track data of the vehicle to be monitored into a track prediction model to obtain the track abnormal probability value of the vehicle to be monitored.
Specifically, after determining the trajectory prediction model corresponding to the vehicle to be monitored, the computer device may input the trajectory data of the vehicle to be monitored into the trajectory prediction model to obtain the trajectory anomaly probability value of the vehicle to be monitored. Then, the computer device can display or output the track abnormality probability value, so that a user can timely know the track abnormality condition of the vehicle to be monitored. In addition, an alarm threshold value can be set, and an alarm prompt is automatically sent out when the track abnormality probability value of the vehicle to be monitored exceeds the alarm threshold value, or the alarm prompt is automatically sent out when the track abnormality probability value of the vehicle to be monitored continuously rises, and the like. It can be understood that there may be many application scenarios of the track anomaly probability value, and this implementation is not illustrated here one by one, and all the conventional data output methods in the prior art are applicable to this embodiment.
The track monitoring method for the operating vehicle provided by the embodiment includes the steps of firstly obtaining track data and a service type of a vehicle to be monitored, then determining a track prediction model corresponding to the vehicle to be monitored according to the service type, and finally obtaining a track abnormal probability value of the vehicle to be monitored through the track prediction model. In the method, the track prediction model is obtained by training based on an isolated forest algorithm and a random forest algorithm, wherein the isolated forest algorithm can separate a normal track and an abnormal track in a sample, so that sufficient pre-judged sample data is provided for the random forest algorithm, and the random forest algorithm can accurately predict the abnormal probability of the track data according to the pre-judged sample data, so that the probability of track abnormality of the operating vehicle is timely and accurately monitored, and the timeliness and the accuracy of the monitoring of the running track of the operating vehicle are effectively improved.
In one embodiment, step 101 may be implemented by: the method comprises the steps of firstly, acquiring position data of a vehicle to be monitored in real time through a GPS device installed on the vehicle to be monitored, then generating a running track of the vehicle to be monitored according to the position data of the vehicle to be monitored acquired in real time, finally selecting a plurality of positioning points from the running track, and generating track data of the vehicle to be monitored according to longitude and latitude coordinate values of the positioning points. The GPS device refers to equipment which is arranged on a vehicle by a vehicle leasing party and used for position monitoring, and is generally divided into an active GPS and a passive GPS, wherein the active GPS needs to be connected with a vehicle battery, and the passive GPS does not need to be connected with the vehicle battery; the driving track refers to a track route formed in the driving process of the vehicle, namely a connecting line formed by the positions of the automobile at each moment; the trajectory data refers to data composed of a plurality of positioning point coordinate values extracted from the travel trajectory. In the embodiment, the track data of the vehicle to be monitored can be generated by extracting the longitude and latitude coordinate values of the positioning points, so that the calculated amount of the track data is reduced, and the timeliness of track monitoring is improved.
In one embodiment, the method for generating trajectory data by selecting an anchor point in step 101 may be implemented as follows: firstly, cutting a running track into n sections, selecting a positioning point from each section of running track to obtain n positioning points of the running track, then performing ascending sequence arrangement on the n positioning points according to the sequence of acquisition time of the n positioning points to obtain the arrangement serial number of the n positioning points, and finally performing weighting processing on the longitude and latitude coordinate absolute values of the n positioning points by taking the arrangement serial number of the n positioning points as a weight to obtain track data of a vehicle to be monitored. In this embodiment, the driving track may be subjected to average interception or random interception, and the locating point may be a median or a random location number, which is not limited herein. It can be understood that, from the viewpoint of improving the accuracy of the positioning point values, the driving trajectory may be averagely intercepted, for example, the average interception is 10 segments, the positioning point may take the median of the longitude and latitude coordinate values of each segment of the trajectory, then the longitude and latitude coordinate values of n positioning points are weighted according to the arrangement serial number, for example, the longitude x 1 and the latitude x 1 of the first positioning point, the longitude x 2 and the latitude x 2 of the second positioning point, and so on, and finally the trajectory data of the vehicle to be monitored is obtained. It should be noted that, the abnormal probability of a track at the start position is small, and the abnormal probability near the end position is increased, and this embodiment may improve the accuracy of abnormal track detection by weighting the coordinate values of the positioning points.
In one embodiment, the method for obtaining the absolute value of the longitude and latitude coordinates in step 101 may be implemented as follows: acquiring a Euclidean distance central point of a city where a vehicle to be detected is located, calculating the distance between the Euclidean distance central point and a preset city central point, and when the distance between the Euclidean distance central point and the city central point is smaller than a preset deviation value, obtaining longitude and latitude coordinate absolute values of n positioning points according to the difference value between the longitude and latitude coordinate values of the n positioning points and the Euclidean distance central point; and when the distance between the Euclidean distance center point and the city center point is not less than the preset deviation value, obtaining the longitude and latitude coordinate absolute values of the n positioning points according to the difference value between the longitude and latitude coordinate values of the n positioning points and the city center point. The euclidean distance center point is a location point that minimizes the total euclidean distance between elements in the data set, and the location point may be used to identify the geographic center or the density center of a group of elements. In this embodiment, the actual situation of each city is different, and therefore the center point of the city is different. For example, for some cities, the vehicle activity areas are gathered and mainly surround the city, and the city center point can be taken as a reference for calculating absolute values of longitude and latitude coordinates at the moment; for other cities, the vehicle moving areas are scattered, and the Euclidean distance central point can be used as a reference for calculating absolute values of longitude and latitude coordinates under the condition, so that the problem of data inclination is avoided. In the embodiment, the reference of the absolute value of the longitude and latitude coordinates is set according to the distance between the Euclidean distance center point and the city center point, so that the accuracy of the value of the coordinate value of the positioning point can be improved, and the accuracy of vehicle track monitoring under different city conditions is improved.
In one embodiment, as shown in fig. 2, the method for training the trajectory prediction model in step 102 may be implemented by:
201. the method comprises the steps of obtaining multiple pieces of historical track data of multiple operating vehicles, classifying the multiple pieces of historical track data according to the service type of each operating vehicle, and obtaining the multiple pieces of historical track data of each service type.
202. And training to obtain a track judgment model corresponding to each business type through an isolated forest algorithm according to a plurality of pieces of historical track data of each business type.
203. And respectively inputting each piece of historical track data of each service type into a track judgment model of the corresponding service type to obtain a track judgment result of each piece of historical track data, wherein the track judgment result comprises normal and abnormal.
204. And training to obtain a track prediction model corresponding to each service type through a random forest algorithm according to a plurality of pieces of historical track data of each service type and a track judgment result of each piece of historical track data.
In the above embodiment, a plurality of areas, a plurality of service types, and a plurality of pieces of historical trajectory data of a plurality of operating vehicles may be collected first, and then the plurality of pieces of historical trajectory data are classified according to the service types, so as to obtain historical trajectory data in each service type, and further, a trajectory judgment model and a trajectory prediction model corresponding to each service type may be trained according to the classified historical trajectory data. The track judgment model is obtained through isolated forest algorithm training, and the track prediction model is obtained through random forest algorithm training. Specifically, the track judgment model can pre-judge the abnormal track of the collected historical track data, so as to obtain the track judgment result (normal or abnormal) of each piece of historical track data, and train multiple decision trees of the random forest according to the pre-judged labeled historical track data (the label is the track judgment result of the historical track data), so as to obtain the track prediction model corresponding to each service type. In addition, according to the embodiment, the track prediction model is obtained by training the isolated forest first and then training the random forest, and the workload of labeling sample data can be effectively reduced, so that the model training speed is increased.
In one embodiment, the method for obtaining the trajectory judgment model through training of the isolated forest algorithm can be realized by the following steps: firstly, a plurality of historical track sample groups are respectively extracted from a plurality of pieces of historical track data of each service type, wherein each historical track sample group comprises a preset number of pieces of historical track data, then, through a recursive algorithm, one piece of historical track data is randomly selected between the maximum value and the minimum value of each historical track sample group to segment the historical track sample groups until each historical track sample group can not be segmented again, a plurality of binary trees corresponding to each service type are obtained, and finally, the plurality of binary trees corresponding to each service type are integrated, and a track judgment model corresponding to each service type is obtained.
In one embodiment, the method for obtaining the trajectory prediction model through random forest algorithm training can be realized by the following steps: firstly, a sample set of a track prediction model is constructed according to a plurality of pieces of historical track data of each service type and a track judgment result of each piece of historical track data, then a plurality of historical track sample groups are extracted from a training set randomly and in a replacement mode, a decision tree is trained according to each historical track sample group to obtain a plurality of decision trees corresponding to each service type, and finally the decision trees corresponding to each service type are integrated to obtain the track prediction model corresponding to each service type.
Further, as a specific implementation of the method shown in fig. 1 and fig. 2, the embodiment provides a track monitoring device for operating a vehicle, as shown in fig. 3, the device includes: a data acquisition module 31, a model determination module 32 and a data processing module 33.
The data acquisition module 31 can be used for acquiring the track data and the service type of the vehicle to be monitored;
the model determining module 32 is configured to determine a trajectory prediction model corresponding to the vehicle to be monitored according to the service type of the vehicle to be monitored, where the trajectory prediction model is obtained by training based on an isolated forest algorithm and a random forest algorithm;
the data processing module 33 may be configured to input the trajectory data of the vehicle to be monitored into the trajectory prediction model, so as to obtain a trajectory anomaly probability value of the vehicle to be monitored.
In a specific application scenario, the data acquisition module 31 may be specifically configured to acquire, in real time, position data of a vehicle to be monitored through a GPS device installed on the vehicle to be monitored, generate a driving track of the vehicle to be monitored according to the position data of the vehicle to be monitored acquired in real time, select a plurality of positioning points from the driving track, and generate track data of the vehicle to be monitored according to longitude and latitude coordinate values of the plurality of positioning points.
In a specific application scenario, the data obtaining module 31 may be specifically configured to intercept the travel track into n segments, select one positioning point from each segment of the travel track to obtain n positioning points of the travel track, perform ascending order arrangement on the n positioning points according to a sequence of acquisition times of the n positioning points to obtain an arrangement serial number of the n positioning points, and perform weighting processing on longitude and latitude coordinate absolute values of the n positioning points by using the arrangement serial number of the n positioning points as a weight to obtain track data of the vehicle to be monitored.
In a specific application scenario, the data obtaining module 31 may be specifically configured to obtain a euclidean distance center point of a city where a vehicle to be detected is located, calculate a distance between the euclidean distance center point and a preset city center point, obtain longitude and latitude coordinate absolute values of n positioning points according to a difference between longitude and latitude coordinate values of the n positioning points and a preset deviation value when the distance between the euclidean distance center point and the city center point is smaller than the preset deviation value, and obtain longitude and latitude coordinate absolute values of the n positioning points according to a difference between the longitude and latitude coordinate values of the n positioning points and the city center point when the distance between the euclidean distance center point and the city center point is not smaller than the preset deviation value.
In a specific application scenario, the apparatus further includes a model training module 34, where the model training module 34 is specifically configured to obtain multiple pieces of historical trajectory data of multiple operating vehicles, classify the multiple pieces of historical trajectory data according to a service type of each operating vehicle to obtain multiple pieces of historical trajectory data of each service type, train the multiple pieces of historical trajectory data of each service type according to the multiple pieces of historical trajectory data of each service type through an isolated forest algorithm to obtain a trajectory judgment model corresponding to each service type, input each piece of historical trajectory data of each service type into a trajectory judgment model corresponding to the service type, respectively, to obtain a trajectory judgment result of each piece of historical trajectory data, where the trajectory judgment result includes normal and abnormal, and obtain, through a random forest algorithm, the trajectory judgment result of each piece of historical trajectory data and each piece of historical trajectory data according to each service type, and training to obtain a track prediction model corresponding to each service type.
In a specific application scenario, the model training module 34 is specifically configured to extract a plurality of historical track sample groups from a plurality of pieces of historical track data of each service type, where each historical track sample group includes a predetermined number of pieces of historical track data, and randomly select one piece of historical track data between a maximum value and a minimum value of each historical track sample group through a recursive algorithm to segment the historical track sample groups until each historical track sample group is not re-segmentable, so as to obtain a plurality of binary trees corresponding to each service type, and integrate the plurality of binary trees corresponding to each service type, so as to obtain a track determination model corresponding to each service type.
In a specific application scenario, the model training module 34 may be specifically configured to construct a sample set of a trajectory prediction model according to a plurality of pieces of historical trajectory data of each service type and a trajectory determination result of each piece of historical trajectory data, randomly and replaceably extract a plurality of historical trajectory sample groups from the training set, train a decision tree according to each historical trajectory sample group to obtain a plurality of decision trees corresponding to each service type, and integrate the plurality of decision trees corresponding to each service type to obtain the trajectory prediction model corresponding to each service type.
It should be noted that other corresponding descriptions of the functional units related to the track monitoring device for operating a vehicle provided in this embodiment may refer to the corresponding descriptions in fig. 1 and fig. 2, and are not described herein again.
Based on the above-mentioned methods shown in fig. 1 and fig. 2, correspondingly, the present embodiment further provides a storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the above-mentioned track monitoring method for the operating vehicle shown in fig. 1 and fig. 2.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, and the software product to be identified may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, or the like), and include several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the method according to the implementation scenarios of the present application.
Based on the above-mentioned methods shown in fig. 1 and fig. 2 and the embodiment of the track monitoring apparatus for operating a vehicle shown in fig. 3, in order to achieve the above-mentioned object, this embodiment further provides an entity device for monitoring a track of an operating vehicle, which may specifically be a personal computer, a server, a smart phone, a tablet computer, a smart watch, or other network devices, and the entity device includes a storage medium and a processor, the storage medium is used for storing a computer program, and the processor is used for executing the computer program to implement the above-mentioned methods shown in fig. 1 and fig. 2.
Optionally, the entity device may further include a user interface, a network interface, a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, and the like. The user interface may include a Display screen (Display), an input unit such as a keypad (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.
Those skilled in the art will appreciate that the physical device structure for monitoring the trajectory of the operating vehicle provided by the present embodiment does not constitute a limitation to the physical device, and may include more or fewer components, or combine some components, or arrange different components.
The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the hardware of the above-mentioned entity device and the software resources to be identified, and supports the operation of the information processing program and other software and/or programs to be identified. The network communication module is used for realizing communication among components in the storage medium and communication with other hardware and software in the information processing entity device.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus a necessary general hardware platform, and can also be implemented by hardware. By applying the technical scheme of the application, the track data and the service type of the vehicle to be monitored are firstly obtained, then the track prediction model corresponding to the vehicle to be monitored is determined according to the service type, and finally the track abnormal probability value of the vehicle to be monitored is obtained through the track prediction model. Compared with the prior art, the method can timely and accurately monitor the probability of track abnormity of the operating vehicle, and further effectively improve the timeliness and accuracy of the running track monitoring of the operating vehicle.
Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.
Claims (10)
1. A method of trajectory monitoring of an operating vehicle, the method comprising:
acquiring track data and a service type of a vehicle to be monitored;
determining a track prediction model corresponding to the vehicle to be monitored according to the service type of the vehicle to be monitored, wherein the track prediction model is obtained based on isolated forest algorithm and random forest algorithm training;
inputting the track data of the vehicle to be monitored into the track prediction model to obtain the track abnormal probability value of the vehicle to be monitored.
2. The method of claim 1, wherein the obtaining trajectory data for a vehicle to be monitored comprises:
acquiring the position data of the vehicle to be monitored in real time through a GPS device arranged on the vehicle to be monitored;
generating a running track of the vehicle to be monitored according to the position data of the vehicle to be monitored, which is acquired in real time;
and selecting a plurality of positioning points from the driving track, and generating track data of the vehicle to be monitored according to the longitude and latitude coordinate values of the positioning points.
3. The method of claim 2, wherein the selecting a plurality of positioning points from the driving track and generating the track data of the vehicle to be monitored according to the longitude and latitude coordinate values of the plurality of positioning points comprises:
intercepting the running track into n sections, and selecting a positioning point from each section of running track to obtain n positioning points of the running track;
according to the sequence of the acquisition time of the n positioning points, performing ascending arrangement on the n positioning points to obtain the arrangement serial numbers of the n positioning points;
and taking the arrangement serial numbers of the n positioning points as weights, and carrying out weighting processing on the longitude and latitude coordinate absolute values of the n positioning points to obtain the track data of the vehicle to be monitored.
4. The method according to claim 3, wherein the method for obtaining absolute values of longitude and latitude coordinates comprises:
acquiring a Euclidean distance center point of a city where a vehicle to be detected is located, and calculating the distance between the Euclidean distance center point and a preset city center point;
when the distance between the Euclidean distance central point and the city central point is smaller than a preset deviation value, obtaining longitude and latitude coordinate absolute values of the n positioning points according to the difference value between the longitude and latitude coordinate values of the n positioning points and the Euclidean distance central point;
and when the distance between the Euclidean distance central point and the city central point is not less than a preset deviation value, obtaining the longitude and latitude coordinate absolute values of the n positioning points according to the difference value between the longitude and latitude coordinate values of the n positioning points and the city central point.
5. The method according to any one of claims 1 to 4, wherein the training method of the trajectory prediction model comprises:
acquiring a plurality of pieces of historical track data of a plurality of operating vehicles, and classifying the plurality of pieces of historical track data according to the service type of each operating vehicle to obtain a plurality of pieces of historical track data of each service type;
training to obtain a track judgment model corresponding to each service type through an isolated forest algorithm according to a plurality of pieces of historical track data of each service type;
respectively inputting each piece of historical track data of each service type into a track judgment model of the corresponding service type to obtain a track judgment result of each piece of historical track data, wherein the track judgment result comprises normal and abnormal;
and training to obtain a track prediction model corresponding to each service type through a random forest algorithm according to a plurality of pieces of historical track data of each service type and a track judgment result of each piece of historical track data.
6. The method as claimed in claim 5, wherein the training to obtain the trajectory judgment model corresponding to each business type through an isolated forest algorithm according to the plurality of pieces of historical trajectory data of each business type includes:
respectively extracting a plurality of historical track sample groups from a plurality of pieces of historical track data of each service type, wherein each historical track sample group comprises a preset amount of historical track data;
randomly selecting a piece of historical track data between the maximum value and the minimum value of each historical track sample group through a recursive algorithm to segment the historical track sample groups until each historical track sample group can not be segmented again, and obtaining a plurality of binary trees corresponding to each service type;
and integrating the multiple binary trees corresponding to each service type to obtain a track judgment model corresponding to each service type.
7. The method as claimed in claim 5, wherein the training to obtain the trajectory prediction model corresponding to each business type through a random forest algorithm according to the plurality of pieces of historical trajectory data of each business type and the trajectory determination result of each piece of historical trajectory data includes:
constructing a sample set of a track prediction model according to a plurality of pieces of historical track data of each service type and a track judgment result of each piece of historical track data;
randomly and retractably extracting a plurality of historical track sample groups from the training set, and training a decision tree according to each historical track sample group to obtain a plurality of decision trees corresponding to each service type;
and integrating the multiple decision trees corresponding to each service type to obtain a track prediction model corresponding to each service type.
8. A trajectory monitoring device for operating a vehicle, the device comprising:
the data acquisition module is used for acquiring the track data and the service type of the vehicle to be monitored;
the model determining module is used for determining a track prediction model corresponding to the vehicle to be monitored according to the service type of the vehicle to be monitored, wherein the track prediction model is obtained based on isolated forest algorithm and random forest algorithm training;
and the data processing module is used for inputting the track data of the vehicle to be monitored into the track prediction model to obtain the track abnormal probability value of the vehicle to be monitored.
9. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, realizing the steps of the method of any one of claims 1 to 7.
10. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 7 when executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111069904.6A CN113792782A (en) | 2021-09-13 | 2021-09-13 | Track monitoring method and device for operating vehicle, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111069904.6A CN113792782A (en) | 2021-09-13 | 2021-09-13 | Track monitoring method and device for operating vehicle, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113792782A true CN113792782A (en) | 2021-12-14 |
Family
ID=79183024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111069904.6A Pending CN113792782A (en) | 2021-09-13 | 2021-09-13 | Track monitoring method and device for operating vehicle, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792782A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114509283A (en) * | 2022-01-05 | 2022-05-17 | 中车唐山机车车辆有限公司 | System fault monitoring method and device, electronic equipment and storage medium |
| CN115640997A (en) * | 2022-10-15 | 2023-01-24 | 河北省交通规划设计研究院有限公司 | Traffic accident risk dynamic identification method and identification model construction method |
| CN115984992A (en) * | 2022-12-22 | 2023-04-18 | 云控智行(上海)汽车科技有限公司 | Method, device and equipment for detecting vehicle operation data |
| CN117077042A (en) * | 2023-10-17 | 2023-11-17 | 北京鑫贝诚科技有限公司 | Rural level crossing safety early warning method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153906A (en) * | 2017-03-21 | 2017-09-12 | 北京工业大学 | A kind of taxi illegal activities decision method and system |
| CN107451593A (en) * | 2017-07-07 | 2017-12-08 | 西安交通大学 | A kind of high-precision GPS localization method based on image characteristic point |
| CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
| CN109785595A (en) * | 2019-02-26 | 2019-05-21 | 成都古河云科技有限公司 | A kind of vehicle abnormality track real-time identification method based on machine learning |
| CN109886724A (en) * | 2018-12-29 | 2019-06-14 | 中南大学 | A kind of resident trip track recognizing method of robustness |
| CN110288032A (en) * | 2019-06-27 | 2019-09-27 | 武汉中海庭数据技术有限公司 | A kind of vehicle driving trace type detection method and device |
| CN111160089A (en) * | 2019-11-22 | 2020-05-15 | 南京航空航天大学 | Trajectory prediction system and method based on different vehicle types |
-
2021
- 2021-09-13 CN CN202111069904.6A patent/CN113792782A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153906A (en) * | 2017-03-21 | 2017-09-12 | 北京工业大学 | A kind of taxi illegal activities decision method and system |
| CN107451593A (en) * | 2017-07-07 | 2017-12-08 | 西安交通大学 | A kind of high-precision GPS localization method based on image characteristic point |
| CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
| CN109886724A (en) * | 2018-12-29 | 2019-06-14 | 中南大学 | A kind of resident trip track recognizing method of robustness |
| CN109785595A (en) * | 2019-02-26 | 2019-05-21 | 成都古河云科技有限公司 | A kind of vehicle abnormality track real-time identification method based on machine learning |
| CN110288032A (en) * | 2019-06-27 | 2019-09-27 | 武汉中海庭数据技术有限公司 | A kind of vehicle driving trace type detection method and device |
| CN111160089A (en) * | 2019-11-22 | 2020-05-15 | 南京航空航天大学 | Trajectory prediction system and method based on different vehicle types |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114509283A (en) * | 2022-01-05 | 2022-05-17 | 中车唐山机车车辆有限公司 | System fault monitoring method and device, electronic equipment and storage medium |
| CN115640997A (en) * | 2022-10-15 | 2023-01-24 | 河北省交通规划设计研究院有限公司 | Traffic accident risk dynamic identification method and identification model construction method |
| CN115984992A (en) * | 2022-12-22 | 2023-04-18 | 云控智行(上海)汽车科技有限公司 | Method, device and equipment for detecting vehicle operation data |
| CN117077042A (en) * | 2023-10-17 | 2023-11-17 | 北京鑫贝诚科技有限公司 | Rural level crossing safety early warning method and system |
| CN117077042B (en) * | 2023-10-17 | 2024-01-09 | 北京鑫贝诚科技有限公司 | Rural level crossing safety early warning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113792782A (en) | Track monitoring method and device for operating vehicle, storage medium and computer equipment | |
| CA3069511C (en) | Distributed data processing systems for processing remotely captured sensor data | |
| CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
| CN112598192B (en) | Method and device for predicting vehicle entering logistics park, storage medium and terminal | |
| CN114841712B (en) | Method and device for determining illegal operation state of network appointment vehicle tour and electronic equipment | |
| EP2495696A1 (en) | Management server, population information calculation management server, zero population distribution area management method, and population information calculation method | |
| CN111639786A (en) | Resource allocation method, device, storage medium and computer equipment | |
| Habtie et al. | Artificial neural network based real-time urban road traffic state estimation framework | |
| CN115083161B (en) | Vehicle stay point evaluation method and device, electronic equipment and readable storage medium | |
| CN115384516A (en) | Tire wear mileage calculation method, device and equipment for transport vehicle | |
| CN112233428A (en) | Traffic flow prediction method, traffic flow prediction device, storage medium and equipment | |
| Wang et al. | GPS‐data‐driven dynamic destination prediction for on‐demand one‐way carsharing system | |
| CN113256405B (en) | Method, device, equipment and storage medium for predicting cheating user concentrated area | |
| CN113822487A (en) | Risk early warning method and device for operating vehicle, storage medium and computer equipment | |
| CN109791677A (en) | System and method for carrying out Geographic Reference and scoring to vehicle data in community | |
| CN116862591A (en) | Information pushing method, device, computer equipment and readable storage medium | |
| CN116664025A (en) | Loading and unloading position point generation method, device and equipment | |
| CN113743815A (en) | Risk monitoring method and device for operating vehicle, storage medium and computer equipment | |
| CN114394099B (en) | Method and device for identifying abnormal running of vehicle, computer equipment and storage medium | |
| CN112053098B (en) | Order processing method, device, server and computer storage medium | |
| Chen et al. | Using data mining techniques on fleet management system | |
| CN103942403A (en) | Method and device for screening mass variables | |
| CN111402575A (en) | Method and device for evaluating traffic running state | |
| CN114339606B (en) | Method, device, storage medium and electronic equipment for determining user position | |
| CN111832599B (en) | Gas station prediction method based on machine learning random forest |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |